Attention focusing mechanisms and domain-informed selection of representations can make real-time vision tasks work with limited computational power. The paper describes ongoing work in distributed real-time vision which aims to use cheap and plentiful workstations and PCs rather than special-purpose hardware. I discuss a system called ARGUS which is inspired by the visual routines theory of human vision. In ARGUS, reactive feature tracking agents maintain minimal, task-dependent descriptions of relevant image features by direct observation of the live video stream. Routines for model-based object recognition operate on these descriptions. Higher-level processing is independent of the maintenance of lower-level representations. This allows the visual subsystem to provide real-time feedback for closed-loop tasks even when high-level perceptual processing is slow compared to video frame rates. Experiments in moving-object recognition are described which demonstrate the strength of this approach in situations where the perceived scene is changing faster than high-level analysis can categorize it.
[1]
Dana H. Ballard,et al.
Animate Vision
,
1991,
Artif. Intell..
[2]
S. Ullman.
Visual routines
,
1984,
Cognition.
[3]
Gregory D. Hager,et al.
A Framework for Real-time Window-Based Tracking Using Off-The-Shelf Hardware
,
1994
.
[4]
A. Treisman,et al.
A feature-integration theory of attention
,
1980,
Cognitive Psychology.
[5]
Ronald C. Arkin,et al.
Temporal coordination of perceptual algorithms for mobile robot navigation
,
1994,
IEEE Trans. Robotics Autom..
[6]
Ian Horswill,et al.
Visual Routines and Visual Search: A Real-Time Implementation and an Automata-Theoretic Analysis
,
1995,
IJCAI.